modified env.yaml, cleaned up structure, made basic API

Author: pupperemeritus

backend/app/api/models/auth.py backend/API.md

@@ -0,0 +1,18 @@
+import pickle
+
+
+class RFModel:
+    def __init__(self):
+        self.model = self.load_model("phish_model.pkl")
+        self.vectorizer = self.load_model("vectorizer.pkl")
+
+    def load_model(self, model_path):
+        with open(model_path, "rb") as f:
+            model = pickle.load(f)
+        return model
+
+    def predict(self, input_data):
+        # Use the loaded model to make predictions on the input data
+        input_vectorized = self.vectorizer.transform(input_data)
+        predictions = self.model.predict(input_data)
+        return predictions

backend/Data/malicious_phish.csv

@@ -0,0 +1,9 @@
+from fastapi import APIRouter
+from app.utils.get_redirected_urls import get_redirected_urls
+
+router = APIRouter()
+
+@router.get("/get_redirected_urls/{url}")
+async def get_redirected_urls_from_url(url: str):
+    return get_redirected_urls(url)
+

backend/app/security/__init__.py backend/app/api/models/__init__.py

@@ -0,0 +1,9 @@
+from fastapi import APIRouter, Depends
+from app.api.models.phish_model import RFModel
+
+router = APIRouter()
+
+
+@router.get("/phish_model")
+async def predict_phish_model(url: str):
+    return RFModel().predict([url])[0]

backend/app/api/models/fraud.py

@@ -1,9 +1,23 @@
 from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+from app.api.routers.get_redirected_urls import router as redirected_urls_router
+from app.api.routers.model_serve import router as model_serve_router
 
 app = FastAPI()
 
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.include_router(redirected_urls_router)
+app.include_router(model_serve_router)
+
 
-# Sample endpoint
 @app.get("/")
 async def read_root():
     return {"message": "Welcome to the Fraud Detection API"}

backend/app/api/models/phish_model.py

@@ -0,0 +1,25 @@
+import requests
+from bs4 import BeautifulSoup
+import urllib.parse
+
+
+def get_redirected_urls(url):
+    try:
+        response = requests.get(url, allow_redirects=False)
+        if response.status_code == 200:
+            soup = BeautifulSoup(response.content, "html.parser")
+            links = soup.find_all("a", href=True)
+            redirected_urls = []
+            for link in links:
+                href = link["href"]
+                full_url = urllib.parse.urljoin(url, href)
+                redirected_url = requests.head(full_url, allow_redirects=True).url
+                if redirected_url != full_url:
+                    redirected_urls.append((full_url, redirected_url))
+            return redirected_urls
+        else:
+            print("Failed to fetch URL:", url)
+            return []
+    except Exception as e:
+        print("An error occurred:", str(e))
+        return []

backend/app/api/models/reports.py

@@ -0,0 +1,83 @@
+name: fds
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - _py-xgboost-mutex=2.0=cpu_0
+  - annotated-types=0.6.0=py311h06a4308_0
+  - anyio=4.3.0=pyhd8ed1ab_0
+  - argon2-cffi=21.3.0=pyhd3eb1b0_0
+  - argon2-cffi-bindings=21.2.0=py311h5eee18b_0
+  - bcrypt=3.2.0=py311h5eee18b_1
+  - beautifulsoup4=4.12.2=py311h06a4308_0
+  - blas=1.0=mkl
+  - bottleneck=1.3.7=py311hf4808d0_0
+  - brotli-python=1.0.9=py311h6a678d5_7
+  - bs4=4.12.2=py38hd3eb1b0_0
+  - bzip2=1.0.8=h5eee18b_5
+  - ca-certificates=2024.3.11=h06a4308_0
+  - certifi=2024.2.2=py311h06a4308_0
+  - cffi=1.16.0=py311h5eee18b_0
+  - charset-normalizer=2.0.4=pyhd3eb1b0_0
+  - click=8.1.7=py311h06a4308_0
+  - cryptography=42.0.5=py311hdda0065_0
+  - exceptiongroup=1.2.0=pyhd8ed1ab_2
+  - fastapi=0.110.2=pyhd8ed1ab_0
+  - h11=0.14.0=py311h06a4308_0
+  - idna=3.7=pyhd8ed1ab_0
+  - intel-openmp=2023.1.0=hdb19cb5_46306
+  - joblib=1.4.0=py311h06a4308_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - libffi=3.4.4=h6a678d5_0
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgfortran-ng=11.2.0=h00389a5_1
+  - libgfortran5=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libuuid=1.41.5=h5eee18b_0
+  - libxgboost=2.0.3=h6a678d5_0
+  - mkl=2023.1.0=h213fc3f_46344
+  - mkl-service=2.4.0=py311h5eee18b_1
+  - mkl_fft=1.3.8=py311h5eee18b_0
+  - mkl_random=1.2.4=py311hdb19cb5_0
+  - ncurses=6.4=h6a678d5_0
+  - numexpr=2.8.7=py311h65dcdc2_0
+  - numpy=1.26.4=py311h08b1b3b_0
+  - numpy-base=1.26.4=py311hf175353_0
+  - openssl=3.0.13=h7f8727e_0
+  - pandas=2.2.1=py311ha02d727_0
+  - passlib=1.7.4=pyhd3eb1b0_0
+  - pip=23.3.1=py311h06a4308_0
+  - py-xgboost=2.0.3=py311h06a4308_0
+  - pycparser=2.21=pyhd3eb1b0_0
+  - pydantic=2.5.3=py311h06a4308_0
+  - pydantic-core=2.14.6=py311hb02cf49_0
+  - pysocks=1.7.1=py311h06a4308_0
+  - python=3.11.9=h955ad1f_0
+  - python-dateutil=2.8.2=pyhd3eb1b0_0
+  - python-tzdata=2023.3=pyhd3eb1b0_0
+  - pytz=2024.1=py311h06a4308_0
+  - readline=8.2=h5eee18b_0
+  - requests=2.31.0=py311h06a4308_1
+  - scikit-learn=1.2.2=py311h6a678d5_1
+  - scipy=1.11.4=py311h08b1b3b_0
+  - setuptools=68.2.2=py311h06a4308_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - sniffio=1.3.1=pyhd8ed1ab_0
+  - soupsieve=2.5=py311h06a4308_0
+  - sqlite=3.41.2=h5eee18b_0
+  - starlette=0.37.2=pyhd8ed1ab_0
+  - tbb=2021.8.0=hdb19cb5_0
+  - threadpoolctl=2.2.0=pyh0d69192_0
+  - tk=8.6.12=h1ccaba5_0
+  - typing-extensions=4.11.0=hd8ed1ab_0
+  - typing_extensions=4.11.0=pyha770c72_0
+  - tzdata=2024a=h04d1e81_0
+  - urllib3=2.1.0=py311h06a4308_1
+  - uvicorn=0.20.0=py311h06a4308_0
+  - wheel=0.41.2=py311h06a4308_0
+  - xgboost=2.0.3=py311h06a4308_0
+  - xz=5.4.6=h5eee18b_0
+  - zlib=1.2.13=h5eee18b_0

backend/app/api/models/rf_model.pkl

@@ -1,6 +1,10 @@
 Ideas
 
-
+- RAG to retrieve known fraud
+- Page Scanner for suspicious redirects
+- model for judging website based on domain name
+- button for reporting fraudulent websites
+- measures to prevent spam of reports by rivals of a website
 
 System design(ig)